© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 40228
    Prev
    Next
    INDEX
    Explanations

    expressions of enjoyment and appreciation for creative works

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    adera
    -0.06
    orial
    -0.06
    alse
    -0.06
    iss
    -0.06
    YS
    -0.06
    ropa
    -0.06
    ãģ»
    -0.06
    δη
    -0.06
    áo
    -0.06
    alo
    -0.05
    POSITIVE LOGITS
    çļĦè¯Ŀ
    0.09
    ÙģÙĤ
    0.08
     yoksa
    0.08
    hdl
    0.07
     využÃŃ
    0.07
    agas
    0.07
    ово
    0.07
    zie
    0.07
     sama
    0.06
    eree
    0.06
    Activations Density 0.006%

    No Known Activations